Compression and Transmission of Facial Images Over Very Narrowband Channels

Abstract

Law enforcement officers on mobile duty are often confronted with ID authentication of subjects, requiring the transmission of a driver's license picture over wireless channels with very narrow bandwidths. To access mug shots in a reliable and timely manner, real time compression and decompression methods with high compression ratios are required at the server database and at the mobile client unit. This thesis presents a methodology, which minimizes the size of the data sent over the channel by locally storing common features of the human face in the client computers. Pre-processing of server database images, such as facial feature extraction, are used to extract these common facial features, and are obtained via topological methods, in particular, via ravine extraction. The implemented file transfer protocols are based on basic TCP/IP client-server models and make use of socket programming. Experimental results show a 4x improvement in transfer time over typically saturated channels.